Data

Tools

Indexes

Applications

Experiments

Open Source Science

uav_classification

Code behind "4,500 Seconds" and "15,500" Seconds. More to come

https://github.com/andrewpberg/uav_classification

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (12.0%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Code behind "4,500 Seconds" and "15,500" Seconds. More to come

Basic Info
  • Host: GitHub
  • Owner: AndrewPBerg
  • License: mit
  • Language: Python
  • Default Branch: master
  • Homepage:
  • Size: 1.27 GB
Statistics
  • Stars: 3
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed 6 months ago
Metadata Files
Readme License Citation

README.md

Spectrogram Dataset 🔉

Images of the feature extracted samples of the Custom UAV dataset can be found at UAV Classification Dataset

Papers 📜

1️⃣ 4,500 Seconds [Accepted, Preprint]: Arxiv 2505.23782
    ↪️4,500 Seconds Oral Presenation: YouTube Link
2️⃣ 15,500 Seconds [Under Review, Preprint]: Arxiv 2506.11049
3️⃣ The Unbearable Weight: TBD

Training Logs 🪵

Weights & Biases Training Logs

UAV Classification 🛩️

Code repository for UAV (Unmanned Aerial Vehicle) classification using deep learning techniques. The project is containerized using Docker and supports experiment tracking with Weights & Biases.

NOTE 📎

The Datasets used in this project are not included in the repository due to their visibility -> We have decided not to open-source the datasets.

If you would like to use the codebase, please use this example directory to store your datasets. and update the config.yaml file to point to your datasets.

Prerequisites 🔮

  • Docker
  • Python 3.8+
  • CUDA-compatible GPU (recommended)

Setup 🏗️

  1. Clone the repository: bash git clone https://github.com/yourusername/UAV_Classification_repo.git cd UAV_Classification_repo

  2. (Optional) Copy the example environment file and configure your variables: bash cp .env.example .env

  3. Build and using Docker:

bash docker compose build app

Environment Variables 📨

Create a .env file in the root directory with the following variables (see .env.example):

Note: see setup section for more details

  • WANDB_API_KEY: Your Weights & Biases API key
  • BOT_TOKEN: Telegram bot token for notifications (optional)
  • CHAT_ID: Telegram chat ID for notifications (optional)

Usage 🐳

  1. Configure your experiment in src/config.yaml & orchestrate.yaml

  2. Run training: bash docker compose run app

    License ⚖️

This project is licensed under the MIT License - see the LICENSE file for details.

Owner

  • Name: Andrew Berg
  • Login: AndrewPBerg
  • Kind: user
  • Location: Charleston, SC

Current Student at College of Charleston, enjoyer of personal projects

Citation (CITATION.cff) 

cff-version: 1.2.0
title: "UAV Classifcation training approaches on small data"
message: >-
  If you use this software, please cite it using the
  metadata from this file.
authors:
  - family-names: Andrew
    given-names: Berg
  - name: ""
abstract:  >-
  Small data approaches to training deep neural networks given a small UAV dataset
license: MIT
license-url: "https://github.com/AndrewPBerg/UAV_Classification/blob/master/LICENSE"
repository-code: "https://github.com/AndrewPBerg/UAV_Classification"
keywords:
  - audio classification
  - UAV
type: software

GitHub Events

Total
  • Issues event: 16
  • Watch event: 6
  • Delete event: 33
  • Member event: 1
  • Public event: 1
  • Push event: 314
  • Pull request review event: 2
  • Pull request event: 53
  • Create event: 34
Last Year
  • Issues event: 16
  • Watch event: 6
  • Delete event: 33
  • Member event: 1
  • Public event: 1
  • Push event: 314
  • Pull request review event: 2
  • Pull request event: 53
  • Create event: 34

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 9
  • Total pull requests: 32
  • Average time to close issues: 18 days
  • Average time to close pull requests: less than a minute
  • Total issue authors: 1
  • Total pull request authors: 1
  • Average comments per issue: 0.0
  • Average comments per pull request: 0.0
  • Merged pull requests: 27
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 9
  • Pull requests: 32
  • Average time to close issues: 18 days
  • Average time to close pull requests: less than a minute
  • Issue authors: 1
  • Pull request authors: 1
  • Average comments per issue: 0.0
  • Average comments per pull request: 0.0
  • Merged pull requests: 27
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • AndrewPBerg (9)
Pull Request Authors
  • AndrewPBerg (32)
Top Labels
Issue Labels
bug (1) wontfix (1)
Pull Request Labels

Dependencies

Dockerfile docker
  • alpine latest build
  • nvidia/cuda 12.1.0-cudnn8-devel-ubuntu20.04 build
  • python 3.11-slim-bullseye build
docker-compose.yml docker
  • ast_container latest
requirements.txt pypi